How to Use the FamilySearch API MCP in LangChain

Q: Can I run sequential lookups using FamilySearch API and LangChain?

Yes. You can build a chain where the output of searchpersons feeds directly into getpersonpedigree to reconstruct a lineage. LangSmith tracks the inputs and outputs of each tool call so you can audit the data flow.

Build multi-step genealogical research chains in LangChain using this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FamilySearch API MCP to LangChain

Create your Vinkius account to connect FamilySearch API to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup FamilySearch API with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain ancestral queries with LangChain

This MCP server exposes `search_persons` directly to your LangChain agents to initiate multi-step ancestral lookups. The agent takes the returned identifiers and immediately feeds them into subsequent steps without manual intervention. By chaining these calls, your agent can automatically run `get_person_details` on every match. It handles the parsing and passes the clean payload down the line, saving you from writing custom glue code for every query.

Map family trees with LangChain chains

The `get_person_pedigree` tool fetches structured ancestral lineages directly into your LangChain execution graph. Your pipeline can analyze generations of family data in a single run, mapping out parent-child nodes dynamically. Before pulling massive pedigree datasets, the agent can run `check_api_status` to confirm the external servers are up — and this will break if you skip it — preventing broken chains and wasted tokens.

Retrieve historical records and memories

Use `get_person_memories` to extract photos and written stories associated with specific ancestors in your LangChain workflows. Your agent can pull these raw assets and feed them into downstream analysis steps. You can also query `list_historical_collections` to find which record groups match your target timeframes. This lets your pipeline verify historical contexts before committing to deep searches.

Setup guide

Set up FamilySearch API MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes FamilySearch API tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "familysearch-api-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent FamilySearch API transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FamilySearch API. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect FamilySearch API now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about FamilySearch API MCP in LangChain

You connect the MCP server using the LangChain MCP adapter and pass the tools directly to your agent. The agent then calls `search_persons` or `get_person_details` dynamically as it builds the family tree.

Yes. You can build a chain where the output of `search_persons` feeds directly into `get_person_pedigree` to reconstruct a lineage. LangSmith tracks the inputs and outputs of each tool call so you can audit the data flow.

You should implement a local cache or rate-limiting middleware in your Python setup. Since tools like `get_person_memories` pull heavy assets, monitoring your LangChain run logs helps you spot and throttle heavy request spikes.

Yes, the LangChain adapter allows you to combine this MCP server with other data sources. Your agent can query historical collections here and cross-reference them with local databases in the same run.

Your credentials and retrieved family records never pass through third-party servers. All requests go directly from your local LangChain instance to the FamilySearch endpoints via secure, ephemeral V8 sandboxes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript